Triple
T12005618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dirty Work |
E285771
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Fight |
E486605
|
NE FINISHED |
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: Fight | Statement: [Dirty Work, hasPart, Fight]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fight Context triple: [Dirty Work, hasPart, Fight]
-
A.
Battle
Battle is a historic market town in East Sussex, England, best known as the site of the 1066 Battle of Hastings.
-
B.
Combat
Combat was a prominent clandestine newspaper of the French Resistance during World War II, known for its role in coordinating and inspiring anti-occupation activities.
-
C.
Combat
Combat is an abstract expressionist painting by American artist Lee Krasner, reflecting her dynamic, gestural style and exploration of emotional intensity.
-
D.
Combat
chosen
Combat is a classic 1977 Atari video game for the Atari 2600 featuring head-to-head tank and aerial combat in a variety of simple, competitive multiplayer modes.
-
E.
Fisticuffs
Fisticuffs is a music production duo known for crafting smooth, R&B-influenced tracks for artists such as Miguel and Jhene Aiko.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ab45a368819084fce08bf0dc3705 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c5cfc08190821e4b2940c51416 |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f48b0574d48190b336a6b9a4ada2a8 |
completed | May 1, 2026, 11:14 a.m. |
Created at: April 8, 2026, 9:46 p.m.