Triple
T26942159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | History of Sindh |
E678549
|
entity |
| Predicate | earliestCivilization |
P108422
|
FINISHED |
| Object | IndusValleyCivilization |
—
|
NE NERFINISHED |
How this triple was built (2 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: IndusValleyCivilization | Statement: [History of Sindh, earliestCivilization, IndusValleyCivilization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earliestCivilization Context triple: [History of Sindh, earliestCivilization, IndusValleyCivilization]
-
A.
earliestKnownCivilization
chosen
Indicates that the subject is recognized as the first or oldest known civilization associated with the object (such as a region, culture, or time period).
-
B.
earliestPermanentSettlement
Indicates that one entity is the location or instance of the first long-term, continuously inhabited settlement associated with another entity.
-
C.
earliestKingdom
Indicates that one kingdom is the chronologically first or oldest among a specified set of kingdoms.
-
D.
earliestMajorEmpire
Indicates that the subject is the earliest major empire associated with, or relevant to, the given object in time.
-
E.
ancientStates
Indicates that the related entity functioned as a state or political entity in ancient times.
- F. None of above.
Provenance (3 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_69eeeb4d69588190a7c912164a1c37b3 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f657f653448190a945b4751af8507d |
completed | May 2, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 6:19 a.m.