Triple
T10679189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harlem Hellfighters |
E251698
|
entity |
| Predicate | timeInCombat |
P95267
|
FINISHED |
| Object | among the longest of any American unit in World War I |
—
|
LITERAL 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: among the longest of any American unit in World War I | Statement: [Harlem Hellfighters, timeInCombat, among the longest of any American unit in World War I]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeInCombat Context triple: [Harlem Hellfighters, timeInCombat, among the longest of any American unit in World War I]
-
A.
sawCombat
Indicates that an entity directly participated in active military or armed conflict.
-
B.
numberLaunchedInCombat
Indicates the quantity of times an entity has been launched or deployed specifically in combat operations.
-
C.
hasCombat
Indicates that an entity engages in, is involved with, or possesses the capability for combat or fighting interactions with other entities.
-
D.
allyInBattle
Indicates that two or more entities cooperate on the same side as partners during a specific battle or combat situation.
-
E.
battleDuration
Indicates the length of time for which a particular battle or combat event lasts.
- F. None of above. chosen
Provenance (4 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_69d6aa5bd7c08190a816e733b4045c23 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fcc03dc4819080a6211a2bfaaf0a |
completed | April 9, 2026, 1:11 a.m. |
| PD | Predicate disambiguation | batch_69d6dd8a93208190a573061387e2aebb |
completed | April 8, 2026, 10:58 p.m. |
| PDg | Predicate description generation | batch_69d6df47899481909ac0e518d94883cb |
completed | April 8, 2026, 11:05 p.m. |
Created at: April 8, 2026, 9:10 p.m.