Triple
T15585042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zola Dam |
E374596
|
entity |
| Predicate | locatedOnWatercourse |
P1489
|
FINISHED |
| Object |
Infernet stream
Infernet stream is a watercourse in France that serves as the river on which the Zola Dam is built.
|
E1165708
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Infernet stream | Statement: [Zola Dam, locatedOnWatercourse, Infernet stream]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Infernet stream Context triple: [Zola Dam, locatedOnWatercourse, Infernet stream]
-
A.
IETF Stream
The IETF Stream is the primary publication channel through which the Internet Engineering Task Force issues its technical standards and best current practice documents as RFCs.
-
B.
Back Stream
Back Stream is a minor watercourse in Somerset, England, that serves as one of the tributaries feeding into the River Tone.
-
C.
IRTF Stream
The IRTF Stream is a publication channel within the Internet Research Task Force used for disseminating research-oriented RFCs produced by IRTF research groups.
-
D.
StarStream Media
StarStream Media is a film and television production company known for backing independent and offbeat projects such as the comedy film "The Little Hours."
-
E.
INETER
INETER is Nicaragua’s national geophysical and meteorological institute responsible for monitoring volcanic, seismic, and other natural hazards across the country.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Infernet stream Triple: [Zola Dam, locatedOnWatercourse, Infernet stream]
Generated description
Infernet stream is a watercourse in France that serves as the river on which the Zola Dam is built.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Infernet stream Target entity description: Infernet stream is a watercourse in France that serves as the river on which the Zola Dam is built.
-
A.
IETF Stream
The IETF Stream is the primary publication channel through which the Internet Engineering Task Force issues its technical standards and best current practice documents as RFCs.
-
B.
Back Stream
Back Stream is a minor watercourse in Somerset, England, that serves as one of the tributaries feeding into the River Tone.
-
C.
IRTF Stream
The IRTF Stream is a publication channel within the Internet Research Task Force used for disseminating research-oriented RFCs produced by IRTF research groups.
-
D.
StarStream Media
StarStream Media is a film and television production company known for backing independent and offbeat projects such as the comedy film "The Little Hours."
-
E.
INETER
INETER is Nicaragua’s national geophysical and meteorological institute responsible for monitoring volcanic, seismic, and other natural hazards across the country.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e47971481909e986dd999354628 |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c4f71e48190a15eb0a2138f083f |
completed | May 9, 2026, 3:01 p.m. |
| NEDg | Description generation | batch_69ff4fb2522481909fa66c2e1fac23bf |
completed | May 9, 2026, 3:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff5238f0e88190b280942022480c12 |
completed | May 9, 2026, 3:26 p.m. |
Created at: April 10, 2026, 4:11 a.m.