Triple
T7376626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pine Island Glacier |
E170140
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object |
PIG
PIG is the commonly used acronym for Pine Island Glacier, one of Antarctica’s largest and fastest-changing glaciers, significant for its impact on global sea-level rise.
|
E659969
|
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: PIG | Statement: [Pine Island Glacier, alsoKnownAs, PIG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PIG Context triple: [Pine Island Glacier, alsoKnownAs, PIG]
-
A.
Pig
Pig is a 2021 neo-noir drama film starring Nicolas Cage as a reclusive truffle hunter searching for his stolen foraging pig.
-
B.
Pigadia
Pigadia is the main town and port of the Greek island of Karpathos, serving as its administrative and commercial center.
-
C.
Pigpile
Pigpile is a live album by the American noise rock band Big Black, capturing one of their final performances with raw, abrasive intensity.
-
D.
Breadpig
Breadpig is a quirky, socially conscious merchandising company and “uncorporation” known for selling geeky products and donating much of its profits to charity.
-
E.
Porco
Porco is a popular nickname for Sociedade Esportiva Palmeiras, one of Brazil’s most successful and traditional football clubs.
- 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: PIG Triple: [Pine Island Glacier, alsoKnownAs, PIG]
Generated description
PIG is the commonly used acronym for Pine Island Glacier, one of Antarctica’s largest and fastest-changing glaciers, significant for its impact on global sea-level rise.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: PIG Target entity description: PIG is the commonly used acronym for Pine Island Glacier, one of Antarctica’s largest and fastest-changing glaciers, significant for its impact on global sea-level rise.
-
A.
Pig
Pig is a 2021 neo-noir drama film starring Nicolas Cage as a reclusive truffle hunter searching for his stolen foraging pig.
-
B.
Pigadia
Pigadia is the main town and port of the Greek island of Karpathos, serving as its administrative and commercial center.
-
C.
Pigpile
Pigpile is a live album by the American noise rock band Big Black, capturing one of their final performances with raw, abrasive intensity.
-
D.
Breadpig
Breadpig is a quirky, socially conscious merchandising company and “uncorporation” known for selling geeky products and donating much of its profits to charity.
-
E.
Porco
Porco is a popular nickname for Sociedade Esportiva Palmeiras, one of Brazil’s most successful and traditional football clubs.
- 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_69c68a5bfaac81909ce7f001dfb70c76 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1a8b18c8190ad1a19521eda2319 |
completed | March 27, 2026, 9:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802d15a8481908e43701459607276 |
completed | March 28, 2026, 4:33 p.m. |
| NEDg | Description generation | batch_69c803ad72308190a9640f2fb043daab |
completed | March 28, 2026, 4:37 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8043121988190b7c9ea0f786296c2 |
completed | March 28, 2026, 4:39 p.m. |
Created at: March 27, 2026, 3:07 p.m.